Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to women and gender-related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     înc
    -0.76
    Dade
    -0.74
    limus
    -0.73
     Tare
    -0.73
     Idy
    -0.71
     nuages
    -0.68
     arbres
    -0.68
     kasarigan
    -0.67
    ValueGenerated
    -0.63
    pendium
    -0.62
    POSITIVE LOGITS
     women
    0.95
     Women
    0.95
    women
    0.93
    Women
    0.90
     WOMEN
    0.89
    WOMEN
    0.83
     Majefty
    0.81
    WOMAN
    0.77
    woman
    0.76
    ResponseWriter
    0.75
    Act Density 0.061%

    No Known Activations